Indoor Location Using Fingerprinting and Fuzzy Logic

Mestre, Pedro; Coutinho, Luis; Reigoto, Luis; Matias, João; Correia, Aldina; Couto, Pedro; Serôdio, Carlos

doi:10.1007/978-3-642-24001-0_33

Cited by 8 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…13, No. 12, December 2018 ©2018 Journal of Communications [20], [25], [31]- [33], [40], [58]- [64] have been compared with the current work in terms of MAE. These studies are similar to our work on indoor environments, adopted wireless technologies (i.e., ZigBee), and artificial intelligent or optimization algorithm.…”

Section: E Comparison Results Between Hybrid Pe-pso and Lnsmmentioning

confidence: 99%

Path Loss Model-Based PSO for Accurate Distance Estimation in Indoor Environments

Hashim¹,

Mohammed²,

Gharghan³

2018

jcm

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) and their applications have received considerable interest in the last few years. In WSNs, accurate path loss models should be considered to achieve a successful distribution of several nodes. In this work, two path loss models are proposed to evaluate the distance between two ZigBee WSNs. First, a path loss model based on conventional Log-Normal Shadowing Model (LNSM) is derived using the collected received signal strength indicator (RSSI) of the ZigBee in real time. Second, a new path loss model based on Particle Swarm Optimization (PSO) algorithm hybridized with Polynomial Equation (PE) is proposed. The PSO algorithm is used to select the optimum coefficients of PE. These coefficients can be utilized to optimize the distance estimation error based on the curve fitting. Therefore, the new path loss model called hybrid PE-PSO is innovated in this work. The hybrid PE-PSO model considerably improves the distance estimation accuracy compared with the LNSM. Results show that the hybrid PE-PSO achieves 85% improvement in distance error compared with the traditional LNSM. The mean absolute error of 0.77 m is obtained for distance estimation, which outperforms that by state of the arts.

show abstract

Section: E Comparison Results Between Hybrid Pe-pso and Lnsmmentioning

confidence: 99%

Path Loss Model-Based PSO for Accurate Distance Estimation in Indoor Environments

Hashim¹,

Mohammed²,

Gharghan³

2018

jcm

View full text Add to dashboard Cite

show abstract

“…The hybrid GSA–ANN algorithm can be compared with previous works [ 9 , 30 , 39 , 46 , 51 , 53 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 ] in terms of localization or distance error to validate our proposed system. Similar studies based on different soft computing techniques were considered for the purposes of comparison.…”

Section: Results Comparisonmentioning

confidence: 99%

A Wireless Sensor Network with Soft Computing Localization Techniques for Track Cycling Applications

Gharghan

Nordin

Ismail

2016

Sensors

View full text Add to dashboard Cite

In this paper, we propose two soft computing localization techniques for wireless sensor networks (WSNs). The two techniques, Neural Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN), focus on a range-based localization method which relies on the measurement of the received signal strength indicator (RSSI) from the three ZigBee anchor nodes distributed throughout the track cycling field. The soft computing techniques aim to estimate the distance between bicycles moving on the cycle track for outdoor and indoor velodromes. In the first approach the ANFIS was considered, whereas in the second approach the ANN was hybridized individually with three optimization algorithms, namely Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), and Backtracking Search Algorithm (BSA). The results revealed that the hybrid GSA-ANN outperforms the other methods adopted in this paper in terms of accuracy localization and distance estimation accuracy. The hybrid GSA-ANN achieves a mean absolute distance estimation error of 0.02 m and 0.2 m for outdoor and indoor velodromes, respectively.

show abstract

“…The objective of this API is to be included in other software packages, to solve problems where derivative based methods cannot be used. It was used in location estimation problems by the authors in Mestre et al (2012Mestre et al ( , 2013 to tune the LEA (Location Estimation Algorithm) and adapt them to the mobile terminals. While in Mestre et al (2012) a Fuzzy Logic based LEA was implemented and the API was used to tune the parameters/transitions of membership functions and adjust the weights of OWA (Ordered Weighted Averaging), in Mestre et al (2013) the API was used to tune the internal parameters of the Weighted k-Nearest Neighbour algorithm and a scaling factor for the RSSI (Received Signal Strength) values.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Penalty and Barrier function based on Fuzzy Logic

Matias

Correia

Mestre

et al. 2015

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

Optimization methods have been used in many areas of knowledge, such as Engineering, Statistics, Chemistry, among others, to solve optimization problems. In many cases it is not possible to use derivative methods, due to the characteristics of the problem to be solved and/or its constraints, for example if the involved functions are non-smooth and/or their derivatives are not know. To solve this type of problems a Java based API has been implemented, which includes only derivative-free optimization methods, and that can be used to solve both constrained and unconstrained problems. For solving constrained problems, the classic Penalty and Barrier functions were included in the API. In this paper a new approach to Penalty and Barrier functions, based on Fuzzy Logic, is proposed. Two penalty functions, that impose a progressive penalization to solutions that violate the constraints, are discussed. The implemented functions impose a low penalization when the violation of the constraints is low and a heavy penalty when the violation is high. Numerical results, obtained using twentyeight test problems, comparing the proposed Fuzzy Logic based functions to six of the classic Penalty and Barrier functions are presented. Considering the achieved results, it can be concluded that the proposed penalty functions besides being very robust also have a very good performance.

show abstract

Indoor Location Using Fingerprinting and Fuzzy Logic

Cited by 8 publications

References 13 publications

Path Loss Model-Based PSO for Accurate Distance Estimation in Indoor Environments

Path Loss Model-Based PSO for Accurate Distance Estimation in Indoor Environments

A Wireless Sensor Network with Soft Computing Localization Techniques for Track Cycling Applications

Adaptive Penalty and Barrier function based on Fuzzy Logic

Contact Info

Product

Resources

About